{"id":"https://openalex.org/W2120573213","doi":"https://doi.org/10.1109/hipc.2009.5433193","title":"Highly scalable algorithm for distributed real-time text indexing","display_name":"Highly scalable algorithm for distributed real-time text indexing","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2120573213","doi":"https://doi.org/10.1109/hipc.2009.5433193","mag":"2120573213"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2009.5433193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.ece.utexas.edu/%7Egarg/dist/hipc09-final.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109064591","display_name":"Ankur Narang","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"funder","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Narang","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004401541","display_name":"Vikas Agarwal","orcid":"https://orcid.org/0000-0002-7719-1066"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"funder","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikas Agarwal","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026548365","display_name":"Monu Kedia","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"funder","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monu Kedia","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061474994","display_name":"Vijay K. Garg","orcid":"https://orcid.org/0000-0002-5797-4389"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"funder","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay K Garg","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.219,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.623497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":82},"biblio":{"volume":null,"issue":null,"first_page":"332","last_page":"341"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9977,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9961,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream Processing","score":0.43641585},{"id":"https://openalex.org/keywords/response-time","display_name":"Response time","score":0.41723022}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.9165117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86240625},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7189053},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4574534},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4545237},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.43641585},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.41723022},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40238136},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3680248},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27544612},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2727687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11447501},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2009.5433193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.8922","pdf_url":"http://www.ece.utexas.edu/%7Egarg/dist/hipc09-final.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.8922","pdf_url":"http://www.ece.utexas.edu/%7Egarg/dist/hipc09-final.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42,"display_name":"Industry, innovation and infrastructure"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":12,"referenced_works":["https://openalex.org/W1578100948","https://openalex.org/W1985102977","https://openalex.org/W2022578651","https://openalex.org/W2073965851","https://openalex.org/W2121854496","https://openalex.org/W2124306283","https://openalex.org/W2135552899","https://openalex.org/W2137077706","https://openalex.org/W2138662031","https://openalex.org/W2140795521","https://openalex.org/W2173213060","https://openalex.org/W3003506064"],"related_works":["https://openalex.org/W4401278057","https://openalex.org/W4237510188","https://openalex.org/W4206019083","https://openalex.org/W3024364549","https://openalex.org/W2370378377","https://openalex.org/W2350613701","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2048865712","https://openalex.org/W1976265003"],"abstract_inverted_index":{"Stream":[0],"computing":[1],"research":[2],"is":[3,232,244,305,315,338,359],"moving":[4],"from":[5,20],"terascale":[6],"to":[7,12,72,160,340],"petascale":[8],"levels.":[9],"It":[10],"aims":[11],"rapidly":[13],"analyze":[14],"data":[15,55,81,201],"as":[16,33,35,82,84],"it":[17,70],"streams":[18],"in":[19,31,131,177,250],"many":[21],"sources":[22],"and":[23,29,38,50,97,148,182,197,207,211,216,258],"make":[24,186,208],"decisions":[25],"with":[26,52,62,114,295,328],"high":[27,53,120,133,278],"speed":[28,121],"accuracy":[30],"fields":[32],"diverse":[34],"security":[36],"surveillance":[37],"financial":[39],"services":[40],"including":[41],"stock":[42],"trading.":[43],"We":[44,218,253,276,332,353],"specifically":[45],"consider":[46],"real-time":[47,123,150],"text":[48,151,209],"indexing":[49,75,88,93,152,180,210,230,240,248,263,279,297,321,347,356,365],"search":[51,105,170,183,330],"input":[54],"rates":[56,76],"(10":[57],"GB/s":[58],"or":[59],"more)":[60],"along":[61],"small":[63],"index":[64,126,178,195,200],"age-off":[65],"(expiry)":[66],"time.":[67,107],"This":[68],"makes":[69],"necessary":[71],"have":[73],"maximal":[74],"for":[77,87,94,100,154],"large":[78,158,326],"volumes":[79],"of":[80,92,145,164,227,247,260,281,311,349],"well":[83],"minimal":[85],"latency":[86,357],"(time":[89],"between":[90],"start":[91],"a":[95,132,251,325],"document":[96],"its":[98],"availability":[99],"search)":[101],"while":[102,166],"maintaining":[103],"very-low":[104],"response":[106,184],"In":[108,138,293],"addition,":[109],"future":[110],"massively":[111],"parallel":[112,155,224,296],"architectures":[113],"storage":[115,135],"class":[116,136],"memories":[117],"will":[118],"enable":[119],"in-memory":[122],"indexing,":[124],"where":[125,242],"can":[127],"be":[128],"completely":[129],"stored":[130],"capacity":[134],"memory.":[137],"this":[139,187,304,314],"paper,":[140],"we":[141],"present":[142],"the":[143,222,245,256,309,316],"design":[144],"distributed":[146,149,229,262],"data-structures":[147],"algorithm":[153,192],"systems":[156],"having":[157],"(thousands":[159],"hundred":[161],"thousand)":[162],"number":[163,246],"cores/processors,":[165],"simultaneously":[167],"providing":[168],"acceptable":[169],"performance":[171,257],"[1].":[172],"The":[173],"inherent":[174],"trade-offs":[175],"involved":[176],"space,":[179],"throughput":[181,280,322,348],"time":[185,225],"problem":[188],"particularly":[189],"challenging.":[190],"Our":[191],"uses":[193],"group-based":[194],"construction":[196],"leverages":[198],"novel":[199],"structures":[202],"that":[203,221,335,358],"reduce":[204],"load":[205],"imbalance":[206],"merge":[212],"process":[213],"more":[214],"scalable":[215,339],"efficient.":[217],"show":[219,334],"analytically":[220],"asymptotic":[223],"complexity":[226],"our":[228,261,312,336],"algorithm,":[231,264],"at":[233,323],"least":[234],"?(log(P))":[235],"factor":[236],"better":[237,362],"than":[238,363],"typical":[239,300,364],"approaches,":[241],"P":[243],"nodes":[249],"group.":[252],"further":[254,333],"demonstrate":[255],"scalability":[259],"on":[265,285,320],"an":[266,286,345],"MPP":[267],"architecture":[268],"(Blue":[269],"Gene/L)":[270],"using":[271,299],"actual":[272],"IBM":[273],"intranet":[274],"data.":[275],"achieved":[277,355],"around":[282,360],"312":[283],"GB/min":[284],"8":[287],"K":[288,342],"node":[289],"Blue":[290],"Gene/L":[291],"machine.":[292],"comparison":[294],"implemented":[298],"approaches":[301],"like":[302],"CLucene,":[303],"3?-7?":[306],"better.":[307],"To":[308],"best":[310],"knowledge,":[313],"first":[317],"published":[318],"result":[319],"such":[324],"scale,":[327],"sustained":[329],"performance.":[331],"approach":[337],"128":[341],"nodes,":[343],"giving":[344],"estimated":[346],"5":[350],"T":[351],"B/min.":[352],"also":[354],"10?":[361],"approaches.":[366]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2120573213","counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-04-22T09:13:09.394039","created_date":"2016-06-24"}